Wav2Vec2-Large-XLSR-53-Spanish
Added custom language model to https://huggingface.co./jonatasgrosman/wav2vec2-large-xlsr-53-spanish
Fine-tuned facebook/wav2vec2-large-xlsr-53 on Spanish using the Common Voice. When using this model, make sure that your speech input is sampled at 16kHz.
This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud :)
The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint
Usage
The model can be used directly (without a language model) as follows...
Using the ASRecognition library:
from asrecognition import ASREngine
asr = ASREngine("es", model_path="jonatasgrosman/wav2vec2-large-xlsr-53-spanish")
audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]
transcriptions = asr.transcribe(audio_paths)
Writing your own inference script:
import torch
import librosa
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
LANG_ID = "es"
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-spanish"
SAMPLES = 10
test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
batch["speech"] = speech_array
batch["sentence"] = batch["sentence"].upper()
return batch
test_dataset = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
with torch.no_grad():
logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
predicted_ids = torch.argmax(logits, dim=-1)
predicted_sentences = processor.batch_decode(predicted_ids)
for i, predicted_sentence in enumerate(predicted_sentences):
print("-" * 100)
print("Reference:", test_dataset[i]["sentence"])
print("Prediction:", predicted_sentence)
Reference | Prediction |
---|---|
HABITA EN AGUAS POCO PROFUNDAS Y ROCOSAS. | HABITAN AGUAS POCO PROFUNDAS Y ROCOSAS |
OPERA PRINCIPALMENTE VUELOS DE CABOTAJE Y REGIONALES DE CARGA. | OPERA PRINCIPALMENTE VUELO DE CARBOTAJES Y REGIONALES DE CARGAN |
PARA VISITAR CONTACTAR PRIMERO CON LA DIRECCIÓN. | PARA VISITAR CONTACTAR PRIMERO CON LA DIRECCIÓN |
TRES | TRES |
REALIZÓ LOS ESTUDIOS PRIMARIOS EN FRANCIA, PARA CONTINUAR LUEGO EN ESPAÑA. | REALIZÓ LOS ESTUDIOS PRIMARIOS EN FRANCIA PARA CONTINUAR LUEGO EN ESPAÑA |
EN LOS AÑOS QUE SIGUIERON, ESTE TRABAJO ESPARTA PRODUJO DOCENAS DE BUENOS JUGADORES. | EN LOS AÑOS QUE SIGUIERON ESTE TRABAJO ESPARTA PRODUJO DOCENA DE BUENOS JUGADORES |
SE ESTÁ TRATANDO DE RECUPERAR SU CULTIVO EN LAS ISLAS CANARIAS. | SE ESTÓ TRATANDO DE RECUPERAR SU CULTIVO EN LAS ISLAS CANARIAS |
SÍ | SÍ |
"FUE ""SACADA"" DE LA SERIE EN EL EPISODIO ""LEAD"", EN QUE ALEXANDRA CABOT REGRESÓ." | FUE SACADA DE LA SERIE EN EL EPISODIO LEED EN QUE ALEXANDRA KAOT REGRESÓ |
SE UBICAN ESPECÍFICAMENTE EN EL VALLE DE MOKA, EN LA PROVINCIA DE BIOKO SUR. | SE UBICAN ESPECÍFICAMENTE EN EL VALLE DE MOCA EN LA PROVINCIA DE PÍOCOSUR |
Evaluation
- To evaluate on
mozilla-foundation/common_voice_6_0
with splittest
python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-spanish --dataset mozilla-foundation/common_voice_6_0 --config es --split test
- To evaluate on
speech-recognition-community-v2/dev_data
python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-spanish --dataset speech-recognition-community-v2/dev_data --config es --split validation --chunk_length_s 5.0 --stride_length_s 1.0
Citation
If you want to cite this model you can use this:
@misc{grosman2021wav2vec2-large-xlsr-53-spanish,
title={XLSR Wav2Vec2 Spanish by Jonatas Grosman},
author={Grosman, Jonatas},
publisher={Hugging Face},
journal={Hugging Face Hub},
howpublished={\url{https://huggingface.co./jonatasgrosman/wav2vec2-large-xlsr-53-spanish}},
year={2021}
}
- Downloads last month
- 21
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Datasets used to train LuisG07/wav2vec2-large-xlsr-53-spanish
Space using LuisG07/wav2vec2-large-xlsr-53-spanish 1
Evaluation results
- Test WER on Common Voice esself-reported8.820
- Test CER on Common Voice esself-reported2.580
- Test WER (+LM) on Common Voice esself-reported6.270
- Test CER (+LM) on Common Voice esself-reported2.060
- Dev WER on Robust Speech Event - Dev Dataself-reported30.190
- Dev CER on Robust Speech Event - Dev Dataself-reported13.560
- Dev WER (+LM) on Robust Speech Event - Dev Dataself-reported24.710
- Dev CER (+LM) on Robust Speech Event - Dev Dataself-reported12.610